Developing an Adaptive AI Agent using Supervised and Reinforcement Learning with Monte Carlo Tree Search in FightingICE.
John Paul Q. TomasNathanael Jhonn R. AguasAngela N. De VillaJasmin Rose G. LimPublished in: CIIS (2021)
Keyphrases
- monte carlo tree search
- reinforcement learning
- temporal difference
- action selection
- multi agent
- reinforcement learning methods
- monte carlo
- bayesian reinforcement learning
- temporal difference learning
- learning agent
- learning algorithm
- supervised learning
- evaluation function
- machine learning
- tree search algorithm
- multi agent systems
- partially observable
- markov decision process
- function approximation
- reinforcement learning algorithms
- optimal policy
- reward function
- learning capabilities
- single agent
- model free
- decision making
- learning process
- action space
- expert systems
- dynamic environments
- transfer learning
- alpha beta search
- control strategies
- markov decision processes